新闻听力 | 如何写提示词
如何写提示词How to write a prompt快速| 六级 易 | 1682词 | 8min30s刘立军供稿Part I. QUESTIONSListen to the lecture and choose the best answer to each question you hear.Q1. What is the primary purpose of the video?A. To introduce the formula for mastering prompts.B. To promote the speaker’s tech skills.C. To share personal anecdotes about tech.D. To compare ChatGPT with Google Bard.Q2. What is the most important component of a good prompt?A. Tone.B. Task.C. Context.D. Persona.Q3. How should the task component be structured?A. With a casual tone.B. With exemplars provided.C. With detailed context.D. With an action verb at the beginning.Q4. What does the speaker imply about the context component in prompts?A. It is optional.B. It is the easiest to get right.C. There is an infinite amount of information you can give.D. It is not as important as the task.Q5. What is the purpose of including exemplars in a prompt?A. To limit the AI's response.B. To improve the quality of the output.C. To provide additional context.D. To give the AI more tasks.Q6. What does the speaker suggest when determining the persona for a prompt?A. Think of a famous person.B. Consider the user’s background.C. Imagine someone with expertise relevant to the task.D. Use a persona only if necessary.Q7. What is an example of a comprehensive prompt given by the speaker?A. I'm a 70 kg male. Give me a 3-month training program.B. I need a report summary. Use H2 for section headers.C. Please provide a list of tone keywords for an email.D. Write an email from Batman for a team offsite.Q8. What does the speaker mean by the format of a prompt?A. The arrangement of the components.B. The desired outcome’s structure and appearance.C. The way the AI should address the user.D. The format in which the prompt is written.Q9. What is the key to using tone effectively in a prompt?A. Matching the tone to the desired output feeling.B. Being formal and professional.C. Using a tone that the AI can understand.D. Avoiding tone-related instructions.Part II. TRANSCRIPTHow to write a promptI don’t usually overhide myself, but in this video, we’re going over the only formula you will ever need to master prompting on ChatGPT and Google Bard. So, let’s get started. Hey friends, welcome back to the channel. If you’re new here, my name is Jeff. I work full time in tech. And if you’re anything like me, a couple months ago, you know prompting is an important skill to learn, but you’re not exactly sure why some prompts generate outputs that are super generic, while others give you precisely what you’re looking for. Since then, I’ve spent hundreds of hours taking prompt engineering courses and applying what I’ve learned in my daily life. (Q1) And so in this video, I’m sharing the six building blocks that make up a good prompt so that you can use this formula to consistently generate high quality outputs. The 6 Prompt ComponentsThe BasicsFirst, it’s critical to not only know what the six components are, task, context, exemplars, persona, format, and tone, but also know that there’s an order of importance to these six components. To show you what I mean, let’s use this simple example. I’m a 70 kg male. Give me a 3-month training program. The first part is context, followed by the task. The reason why the task is higher up in the form, the hierarchy, is if we just input the task without the context, there’s still some sort of meaningful output. But if we just give ChatGPT the context, nothing really happens. Put another way, (Q2)it’s mandatory to have a task in your process prompt. It’s important to include relevant context and exemplars. And it’s nice to have persona, format, and tone. When you think of writing your prompt, go down this mental checklist. So this formula will act as a constant reminder for you to include just enough relevant information when writing prompts. And as you’ll see in this next part, you do not need all six components in every prompt to have a good output. mandatory adj. 强制的,义务的#1 TASKNow let’s break down each building block with specific examples. (Q3) Starting with the task, the rule of thumb is to always start the task sentence with an action verb, generate, give, write, analyze, etc., and clearly articulate what your end goal is. It could be one simple task like generating a three-month training program or a complex three-step task like analyzing hundreds of user feedback, sharing the top three takeaways, and categorizing the feedback based on the team responsible for following up. #2 CONTEXT(Q4) The second component, context, is the trickiest to get right because technically there’s an infinite amount of information you can give. So I found asking myself these three questions to be super helpful in coming up with just enough information to get a good result from ChatGPT. First, what’s the user’s background? Second, what does success look like? And third, what environment are they in? Back to the workout example we now have, I’m a 70 kg male looking to put on 5 kg of muscle mass over the next three months. I only have time to go to the gym twice a week and for one hour each session. Give me a three-month training program to follow. Could I have added more background information? Of course, only prioritize the muscle groups that make me look good on Instagram. But the key to staying productive with ChatGPT and Bard is giving just enough information to constrain the endless possibilities. By the way, although this video is not sponsored, it is supported by those of you who subscribe to my paid productivity newsletter on Google Workspace Tips. Link in the description to learn more. #3 EXEMPLARS = EXEMPLESMoving over to the exemplars component, it’s just a fancy way of saying examples. (Q5) Basically all the research on large language models, LLMs, have shown that including examples within the prompt drastically improves the quality of the output. Starting with a simple example, this is a poorly written bullet point from a resume. We can now ask ChatGPT to rewrite this bullet point using this structure. I accomplished X by the measure Y that resulted in Z, which is actually best practice by the way, so actually do this in your resume. For example, I lowered hospital mortality rate by 10% by educating nurses in new protocols, which translates to 200 lives saved per year. exemplar n. 范例,样本Here’s a slightly more complicated example for interview prep. Based on my own resume, write me an answer to the interview question. What’s your biggest weakness? Use the STAR answer framework, situation, task, action, and results. Here instead of using a full blown interview answer as an example, which would be overkill, the STAR framework acts as an example structure for ChatGPT to follow. overkill n. 过度,过犹不及Last example, let’s say you need to write a job description. You give some context around the opening and ask ChatGPT to reference an existing job description. You might use this one I found on LinkedIn. The output will follow the same formatting and use the same professional HRE language, saving me a bunch of time. Main takeaway here, exemplars are not necessary for every prompt, but including a relevant example or framework will greatly improve the quality of your output. #4 PERSONAMoving along, the persona component is basically who you want ChatGPT and Bard to be. (Q6) And the pro tip here is to think of someone you wish you had instant access to with the task you’re facing. If you injured yourself working out, that person might be a physical therapist with experience helping athletes recover. If you’re a job seeker, that person might be a recruiter or hiring manager. If you’re working on a creative brief, that person might be a senior product marketing manager who’s great at storytelling. Pro tip, you can also name specific individuals, but I found the results to be good only when they’re famous enough, like Warren Buffett, Steve Jobs, Jeff Su. By the way, I just have to share this. We have a team offsite with a superhero’s theme. (Q7) So I asked ChatGPT to draft an email from Batman and it even included things like, please let Alfred know and signed off as the Dark Knight. So fictional characters work as well. And I’m actually going to use this. persona n. 角色,人物形象#5 FORMAT(Q8) The fifth component, format. The pro tip here is to literally close your eyes and visualize how exactly you want the end result to look like. A million likes on my Thirst Bomb Instagram photo. Damn it, didn’t work. Back to the user feedback example, I don’t want to read each sentence. So I asked ChatGPT to take all the feedback and output a table with three headers. The original feedback, the team responsible for following up and priority. And now I can copy this directly and paste it into a Google sheet. So by priority and filter by team. Other common formats include emails, bullet points, and code blocks. header n. 标题,标头But the one I found to be the most useful as a full-time working professional is paragraphs and markdown. For example, I just received a lengthy industry report from my director. First give me the three key takeaways, then summarize based on topic. Use H2 as section headers. Here is the report. Pro tip, whenever I use ChatGPT to proofread any document, I specify that all changes need to be bolded so I can easily see exactly what has been changed. #6 TONELet’s quickly go through the last component, tone, before we put all this together in one example. (Q9) The good news is tone is easy to understand. Use a casual or formal tone of voice. Give me a witty output, show enthusiasm, sound pessimistic. The bad news is we’re usually not very good at recalling the thousands of potential adjectives and adverbs at a moment’s notice. (Q10) So here’s a pro tip. Tell ChatGPT the feeling you’re going for. For example, I’m writing an email to a team I haven’t worked with before and I want to be taken seriously without coming off as too stuck up and cringy. Can you please give me a list of five tone keywords I can include in a prompt for ChatGPT? And look, now in the actual prompt, I can say, use clear and concise language and write in a friendly yet confident tone. EXAMPLE PROMPTPutting all this together, let’s look at this comprehensive prompt. You are a senior product marketing manager at Apple [Persona] and you have just unveiled the latest Apple product in collaboration with Tesla, the Apple Car, and received 12,000 pre-orders, which is 200% higher than target. [Context] Write an email to your boss, Tim Cookie, sharing this positive news. [Task and Format], The email should include a TLDR, too long, didn’t read section. Project background, why this product came into existence, business results section, quantifiable business metrics, and end with a section thanking the product and engineering teams. [Example structure] Use clear and concise language and write in a confident yet friendly tone. [Tone] Note that if I had an existing email to reference, I could delete the instructions around the structure and simply tell ChatGPT the email should follow the exact same format as the one I will share below and paste the email from before. By the way, you can compare the output from this prompt to that of a simpler prompt. I just launched a new product, the Apple car. I received 12,000 pre-orders. Please run email to my boss with this update. There’s a pretty big difference in terms of how generic and usable the end result is. Now that you know the basics of prompting, my next video is going to take you from beginner to pro, so make sure you’re subscribed for that. Check out my top 5 ChatGPT productivity tips for work. See you on the next video. In the meantime, have a great one.Part III. KEYQ1. A. 主旨题。根据“I’m sharing the six building blocks that make up a good prompt so that you can use this formula to consistently generate high quality outputs.”可知是视频的主要目的是分分享构成优质提示的六个核心要素,让大家能用这个公式持续生成高质量内容。因此答案为A。Q2. B. 细节题。根据“it’s mandatory to have a task in your process prompt”可知提示中必须有一个任务,这表明任务是最重要的组成部分。因此答案为B。Q3.D. 细节题。根据“Starting with the task, the rule of thumb is to always start the task sentence with an action verb...”可知任务部分应该以一个动作动词开头。因此答案为D。Q4. C. 细节题。根据“The second component, context, is the trickiest to get right because technically there’s an infinite amount of information you can give.”可知上下文是最棘手的,因为理论上,你可以提供无限量的信息。这表明上下文部分可以有无限的信息。因此答案为C。Q5. B. 细节题。根据“Basically all the research on large language models, LLMs, have shown that including examples within the prompt drastically improves the quality of the output.”可知研究表明,在提示中包含示例能大幅提升输出质量。因此答案为B。Q6. C. 细节题。根据“And the pro tip here is to think of someone you wish you had instant access to with the task you’re facing.”可知讲话者建议确定提示的人物角色时,应该设定为一个与任务相关的专业人士。因此答案为C。Q7. D. 细节题。根据“So I asked ChatGPT to draft an email from Batman and it even included things like, please let Alfred know and signed off as the Dark Knight.”可知讲话者提到,他让ChatGPT起草一封来自蝙蝠侠的电子邮件,包含了请通知阿尔弗雷德并以黑暗骑士的名义签字等细节,这是给出的一个综合提示的例子,其中包含了任务、角色和场景3个要素。因此答案为D。Q8. B. 细节题。根据“The fifth component, format. The pro tip here is to literally close your eyes and visualize how exactly you want the end result to look like.” 可知格式是闭眼能想象到最终结果的样子,也就是输出结果的预期结构和外观。因此答案为B。Q9. B. 推理题。根据“So here’s a pro tip. Tell ChatGPT the feeling you’re going for.”可知在使用提示时,应该指定输出的期望情感,即语气应该与输出的预期感觉相匹配。因此答案为B。 (本文图片来源于摄图网,版权归摄图网所有)